Related papers: Self-Reinforced Cascaded Regression for Face Align…

After four decades of research there still exists a Classification accuracy gap of about 20% between our best Unsupervisedly Learned Representations methods and the accuracy rates achieved by intelligent animals. It thus may well be that we…

Face alignment is crucial for face recognition and has been widely adopted. However, current practice is too simple and under-explored. There lacks an understanding of how important face alignment is and how it should be performed, for…

Gradient-descent methods have exhibited fast and reliable performance for image alignment in the facial domain, but have largely been ignored by the broader vision community. They require the image function be smooth and (numerically)…

We propose a new cascaded regressor for eye center detection. Previous methods start from a face or an eye detector and use either advanced features or powerful regressors for eye center localization, but not both. Instead, we detect the…

We study counterfactual regression, which aims to map input features to outcomes under hypothetical scenarios that differ from those observed in the data. This is particularly useful for decision-making when adapting to sudden shifts in…

In this paper, we propose a framework for disentangling the appearance and geometry representations in the face recognition task. To provide supervision for this aim, we generate geometrically identical faces by incorporating spatial…

Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous…

The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the environment. In most cases, the representations learned purely by the reinforcement learning loss can…

We present a new Cascaded Shape Regression (CSR) architecture, namely Dynamic Attention-Controlled CSR (DAC-CSR), for robust facial landmark detection on unconstrained faces. Our DAC-CSR divides facial landmark detection into three cascaded…

In self-supervised representation learning, a common idea behind most of the state-of-the-art approaches is to enforce the robustness of the representations to predefined augmentations. A potential issue of this idea is the existence of…

Neuroscientists postulate 3D representations in the brain in a variety of different coordinate frames (e.g. 'head-centred', 'hand-centred' and 'world-based'). Recent advances in reinforcement learning demonstrate a quite different approach…

In this work we focus on learning facial representations that can be adapted to train effective face recognition models, particularly in the absence of labels. Firstly, compared with existing labelled face datasets, a vastly larger…

Recent studies in deepfake detection have yielded promising results when the training and testing face forgeries are from the same dataset. However, the problem remains challenging when one tries to generalize the detector to forgeries…

Self-supervised representation learning is heavily dependent on data augmentations to specify the invariances encoded in representations. Previous work has shown that applying diverse data augmentations is crucial to downstream performance,…

Feature transformation aims to generate new pattern-discriminative feature space from original features to improve downstream machine learning (ML) task performances. However, the discrete search space for the optimal feature explosively…

In recent years, image generation has made great strides in improving the quality of images, producing high-fidelity ones. Also, quite recently, there are architecture designs, which enable GAN to unsupervisedly learn the semantic…

Self-supervised learning of convolutional neural networks can harness large amounts of cheap unlabeled data to train powerful feature representations. As surrogate task, we jointly address ordering of visual data in the spatial and temporal…

Despite the success of deep-learning models in many tasks, there have been concerns about such models learning shortcuts, and their lack of robustness to irrelevant confounders. When it comes to models directly trained on human faces, a…

While deep face recognition models have demonstrated remarkable performance, they often struggle on the inputs from domains beyond their training data. Recent attempts aim to expand the training set by relying on computationally expensive…

Visual place recognition is a critical task in computer vision, especially for localization and navigation systems. Existing methods often rely on contrastive learning: image descriptors are trained to have small distance for similar images…